Computer-aided synthesis planning (CASP) algorithms have demonstrated expert-level abilities in planning retrosynthetic routes to molecules of low to moderate complexity. However, current search methods assume the sufficiency of reaching arbitrary building blocks, failing to address the common real-world constraint where using specific molecules is desired. To this end, we present a formulation of synthesis planning with starting material constraints. Under this formulation, we propose Double-Ended Synthesis Planning (DESP), a novel CASP algorithm under a bidirectional graph search scheme that interleaves expansions from the target and from the goal starting materials to ensure constraint satisfiability. The search algorithm is guided by a goal-conditioned cost network learned offline from a partially observed hypergraph of valid chemical reactions. We demonstrate the utility of DESP in improving solve rates and reducing the number of search expansions by biasing synthesis planning towards expert goals on multiple new benchmarks. DESP can make use of existing one-step retrosynthesis models, and we anticipate its performance to scale as these one-step model capabilities improve.
Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
Shanghai Jiao Tong University（上海交通大学）；Shanghai Innovation Institute（上海创新研究院）；East China Normal University（华东师范大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息学院）；School of Physics, Mathematics and Computing, The University of Western Australia（西澳大学物理、数学与计算学院）
Potentially Guided Bidirectionalized RRT* for Fast Optimal Path Planning in Cluttered Environments
National University of Sciences And Technology (NUST)（国立科技大学）；University of California San Diego（加州大学圣迭戈分校）；Manchester Metropolitan University (MMU)（曼彻斯特城市大学）
Bidirectional Task-Motion Planning Based on Hierarchical Reinforcement Learning for Strategic Confrontation
School of Automation Science and Electrical Engineering, Beihang University（自动化科学与电气工程学院，北京航空航天大学）；Advanced Research Institute of Multidisciplinary Sciences and State Key Laboratory of CNS/ATM, Beijing Institute of Technology（多学科科学先进研究院和 CNS/ATM 国家重点实验室，北京理工大学）
Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
Department of Neurobiology, Harvard Medical School（哈佛医学院神经生物学系）；Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University（哈佛大学自然与人工智能研究学院）；Department of Mathematics, NTNU（NTNU数学系）；School of Computer Science, McGill University & Mila（麦吉尔大学计算机科学学院及Mila）；Department of Computer Science, University of Toronto（多伦多大学计算机科学系）；Biophysics Graduate Program, Harvard University（哈佛大学生物物理学研究生项目）
我们在无模型和基于模型的强化学习设置中重新审视残差算法。我们提出了双向目标网络技术来稳定残差算法，产生DDPG的残差版本，在DeepMind Control Suite基准测试中显著优于vanilla DDPG。此外，我们发现残差算法是一种有效的方法，分布失配问题的基于模型的规划。与现有的TD（$k$）方法相比，我们的残差为基础的方法，使更弱的假设模型，并产生更大的性能提升。
